← Search

Martin Woolf

1 accepted papers

2016

Ranking the parameters of deep neural networks using the fisher information

ICASSP 2016accepted

The large number of parameters in deep neural networks (DNNs) often makes them prohibitive for low-power devices, such as field-programmable gate arrays (FPGA). In this paper, we propose a method to determine the relative importance of all network parameters by measuring the amount of information th…

Cited by 0SourceScholar